diff --git a/python/paddle/nn/layer/rnn.py b/python/paddle/nn/layer/rnn.py index 09a0d3cb41cbcb1a867e2e61e37946bf0d059805..e0206b2078db00ba8a2d28d986a421d2543112b2 100644 --- a/python/paddle/nn/layer/rnn.py +++ b/python/paddle/nn/layer/rnn.py @@ -1148,13 +1148,13 @@ class SimpleRNN(RNNBase): None). For more information, please refer to :ref:`api_guide_Name`. Inputs: - - **inputs** (Tensor): the input sequence. If `time_major` is True, the shape is `[time_steps, batch_size, input_size]`, else, the shape is `[batch_size, time_steps, hidden_size]`. + - **inputs** (Tensor): the input sequence. If `time_major` is True, the shape is `[time_steps, batch_size, input_size]`, else, the shape is `[batch_size, time_steps, hidden_size]`. `time_steps` means the length of the input sequence. - **initial_states** (Tensor, optional): the initial state. The shape is `[num_layers * num_directions, batch_size, hidden_size]`. If initial_state is not given, zero initial states are used. - **sequence_length** (Tensor, optional): shape `[batch_size]`, dtype: int64 or int32. The valid lengths of input sequences. Defaults to None. If `sequence_length` is not None, the inputs are treated as padded sequences. In each input sequence, elements whose time step index are not less than the valid length are treated as paddings. Returns: - - **outputs** (Tensor): the output sequence. If `time_major` is True, the shape is `[time_steps, batch_size, num_directions * hidden_size]`, else, the shape is `[batch_size, time_steps, num_directions * hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" else 1. + - **outputs** (Tensor): the output sequence. If `time_major` is True, the shape is `[time_steps, batch_size, num_directions * hidden_size]`, else, the shape is `[batch_size, time_steps, num_directions * hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" else 1. `time_steps` means the length of the output sequence. - **final_states** (Tensor): final states. The shape is `[num_layers * num_directions, batch_size, hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" (the index of forward states are 0, 2, 4, 6... and the index of backward states are 1, 3, 5, 7...), else 1. @@ -1264,13 +1264,13 @@ class LSTM(RNNBase): None). For more information, please refer to :ref:`api_guide_Name`. Inputs: - - **inputs** (Tensor): the input sequence. If `time_major` is True, the shape is `[time_steps, batch_size, input_size]`, else, the shape is `[batch_size, time_steps, hidden_size]`. + - **inputs** (Tensor): the input sequence. If `time_major` is True, the shape is `[time_steps, batch_size, input_size]`, else, the shape is `[batch_size, time_steps, hidden_size]`. `time_steps` means the length of the input sequence. - **initial_states** (list|tuple, optional): the initial state, a list/tuple of (h, c), the shape of each is `[num_layers * num_directions, batch_size, hidden_size]`. If initial_state is not given, zero initial states are used. - **sequence_length** (Tensor, optional): shape `[batch_size]`, dtype: int64 or int32. The valid lengths of input sequences. Defaults to None. If `sequence_length` is not None, the inputs are treated as padded sequences. In each input sequence, elements whos time step index are not less than the valid length are treated as paddings. Returns: - - **outputs** (Tensor): the output sequence. If `time_major` is True, the shape is `[time_steps, batch_size, num_directions * hidden_size]`, If `time_major` is False, the shape is `[batch_size, time_steps, num_directions * hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" else 1. + - **outputs** (Tensor): the output sequence. If `time_major` is True, the shape is `[time_steps, batch_size, num_directions * hidden_size]`, If `time_major` is False, the shape is `[batch_size, time_steps, num_directions * hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" else 1. `time_steps` means the length of the output sequence. - **final_states** (tuple): the final state, a tuple of two tensors, h and c. The shape of each is `[num_layers * num_directions, batch_size, hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" (the index of forward states are 0, 2, 4, 6... and the index of backward states are 1, 3, 5, 7...), else 1. @@ -1371,13 +1371,13 @@ class GRU(RNNBase): None). For more information, please refer to :ref:`api_guide_Name`. Inputs: - - **inputs** (Tensor): the input sequence. If `time_major` is True, the shape is `[time_steps, batch_size, input_size]`, else, the shape is `[batch_size, time_steps, hidden_size]`. + - **inputs** (Tensor): the input sequence. If `time_major` is True, the shape is `[time_steps, batch_size, input_size]`, else, the shape is `[batch_size, time_steps, hidden_size]`. `time_steps` means the length of the input sequence. - **initial_states** (Tensor, optional): the initial state. The shape is `[num_layers * num_directions, batch_size, hidden_size]`. If initial_state is not given, zero initial states are used. Defaults to None. - **sequence_length** (Tensor, optional): shape `[batch_size]`, dtype: int64 or int32. The valid lengths of input sequences. Defaults to None. If `sequence_length` is not None, the inputs are treated as padded sequences. In each input sequence, elements whos time step index are not less than the valid length are treated as paddings. Returns: - - **outputs** (Tensor): the output sequence. If `time_major` is True, the shape is `[time_steps, batch_size, num_directions * hidden_size]`, else, the shape is `[batch_size, time_steps, num_directions * hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" else 1. + - **outputs** (Tensor): the output sequence. If `time_major` is True, the shape is `[time_steps, batch_size, num_directions * hidden_size]`, else, the shape is `[batch_size, time_steps, num_directions * hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" else 1. `time_steps` means the length of the output sequence. - **final_states** (Tensor): final states. The shape is `[num_layers * num_directions, batch_size, hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" (the index of forward states are 0, 2, 4, 6... and the index of backward states are 1, 3, 5, 7...), else 1. diff --git a/python/paddle/text/datasets/wmt16.py b/python/paddle/text/datasets/wmt16.py index f95cbe771cadc834a4de697660caa22a0729521e..2935abeed712a9ea0de4838571ea39c6b6407b34 100644 --- a/python/paddle/text/datasets/wmt16.py +++ b/python/paddle/text/datasets/wmt16.py @@ -71,7 +71,10 @@ class WMT16(Dataset): :attr:`data_file` is not set. Default True Returns: - Dataset: instance of WMT16 dataset + Dataset: instance of WMT16 dataset. The instance of dataset has 3 fields: + - src_ids (np.array) - The sequence of token ids of source language. + - trg_ids (np.array) - The sequence of token ids of target language. + - trg_ids_next (np.array) - The next sequence of token ids of target language. Examples: